Search Results for author:
Found 369 papers, 159 papers with code
Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition
Recognizing irregular text in natural scene images is challenging due to the large variance in text appearance, such as curvature, orientation and distortion.
Ranked #26 on
Scene Text Recognition
on ICDAR2015
Twins: Revisiting the Design of Spatial Attention in Vision Transformers
Very recently, a variety of vision transformer architectures for dense prediction tasks have been proposed and they show that the design of spatial attention is critical to their success in these tasks.
Ranked #48 on
Semantic Segmentation
on ADE20K val
FCOS: Fully Convolutional One-Stage Object Detection
By eliminating the predefined set of anchor boxes, FCOS completely avoids the complicated computation related to anchor boxes such as calculating overlapping during training.
Ranked #4 on
Pedestrian Detection
on TJU-Ped-campus
NAS-FCOS: Fast Neural Architecture Search for Object Detection
The success of deep neural networks relies on significant architecture engineering.
Ranked #113 on
Object Detection
on COCO test-dev
SOLO: Segmenting Objects by Locations
We present a new, embarrassingly simple approach to instance segmentation in images.
Ranked #67 on
Instance Segmentation
on COCO test-dev
SOLOv2: Dynamic and Fast Instance Segmentation
Importantly, we take one step further by dynamically learning the mask head of the object segmenter such that the mask head is conditioned on the location.
Ranked #10 on
Real-time Instance Segmentation
on MSCOCO
BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation
We propose to treat these spatial details and categorical semantics separately to achieve high accuracy and high efficiency for realtime semantic segmentation.
Ranked #1 on
Real-Time Semantic Segmentation
on COCO-Stuff
Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network
Recently, some methods have been proposed to tackle arbitrary-shaped text detection, but they rarely take the speed of the entire pipeline into consideration, which may fall short in practical applications. In this paper, we propose an efficient and accurate arbitrary-shaped text detector, termed Pixel Aggregation Network (PAN), which is equipped with a low computational-cost segmentation head and a learnable post-processing.
Ranked #8 on
Scene Text Detection
on SCUT-CTW1500
DirectPose: Direct End-to-End Multi-Person Pose Estimation
We propose the first direct end-to-end multi-person pose estimation framework, termed DirectPose.
Ranked #13 on
Keypoint Detection
on COCO test-dev
BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation
The proposed BlendMask can effectively predict dense per-pixel position-sensitive instance features with very few channels, and learn attention maps for each instance with merely one convolution layer, thus being fast in inference.
Ranked #13 on
Real-time Instance Segmentation
on MSCOCO
ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network
Our contributions are three-fold: 1) For the first time, we adaptively fit arbitrarily-shaped text by a parameterized Bezier curve.
Ranked #9 on
Text Spotting
on Inverse-Text
Conditional Convolutions for Instance Segmentation
We propose a simple yet effective instance segmentation framework, termed CondInst (conditional convolutions for instance segmentation).
Mask Encoding for Single Shot Instance Segmentation
To date, instance segmentation is dominated by twostage methods, as pioneered by Mask R-CNN.
BoxInst: High-Performance Instance Segmentation with Box Annotations
We present a high-performance method that can achieve mask-level instance segmentation with only bounding-box annotations for training.
FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions
We propose a fully convolutional multi-person pose estimation framework using dynamic instance-aware convolutions, termed FCPose.
Dense Contrastive Learning for Self-Supervised Visual Pre-Training
Compared to the baseline method MoCo-v2, our method introduces negligible computation overhead (only <1% slower), but demonstrates consistently superior performance when transferring to downstream dense prediction tasks including object detection, semantic segmentation and instance segmentation; and outperforms the state-of-the-art methods by a large margin.
Images Speak in Images: A Generalist Painter for In-Context Visual Learning
In this work, we present Painter, a generalist model which addresses these obstacles with an "image"-centric solution, that is, to redefine the output of core vision tasks as images, and specify task prompts as also images.
Ranked #6 on
Personalized Segmentation
on PerSeg
SegGPT: Segmenting Everything In Context
We unify various segmentation tasks into a generalist in-context learning framework that accommodates different kinds of segmentation data by transforming them into the same format of images.
Ranked #1 on
Few-Shot Semantic Segmentation
on PASCAL-5i (5-Shot)
(using extra training data)
Channel-wise Knowledge Distillation for Dense Prediction
Observing that in semantic segmentation, some layers' feature activations of each channel tend to encode saliency of scene categories (analogue to class activation mapping), we propose to align features channel-wise between the student and teacher networks.
Knowledge Adaptation for Efficient Semantic Segmentation
To tackle this dilemma, we propose a knowledge distillation method tailored for semantic segmentation to improve the performance of the compact FCNs with large overall stride.
Enforcing geometric constraints of virtual normal for depth prediction
Monocular depth prediction plays a crucial role in understanding 3D scene geometry.
Ranked #10 on
Depth Estimation
on NYU-Depth V2
Learning to Recover 3D Scene Shape from a Single Image
Despite significant progress in monocular depth estimation in the wild, recent state-of-the-art methods cannot be used to recover accurate 3D scene shape due to an unknown depth shift induced by shift-invariant reconstruction losses used in mixed-data depth prediction training, and possible unknown camera focal length.
Ranked #1 on
Indoor Monocular Depth Estimation
on DIODE
(using extra training data)
Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction
In this work, we show the importance of the high-order 3D geometric constraints for depth prediction.
Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image
To do so, we propose a two-stage framework that first predicts depth up to an unknown scale and shift from a single monocular image, and then exploits 3D point cloud data to predict the depth shift and the camera's focal length that allow us to recover 3D scene shapes.
PolarMask: Single Shot Instance Segmentation with Polar Representation
In this paper, we introduce an anchor-box free and single shot instance segmentation method, which is conceptually simple, fully convolutional and can be used as a mask prediction module for instance segmentation, by easily embedding it into most off-the-shelf detection methods.
Ranked #100 on
Instance Segmentation
on COCO test-dev
Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections
In this work, we propose a very deep fully convolutional auto-encoder network for image restoration, which is a encoding-decoding framework with symmetric convolutional-deconvolutional layers.
Ranked #2 on
Grayscale Image Denoising
on BSD200 sigma10
MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices
We present MobileVLM, a competent multimodal vision language model (MMVLM) targeted to run on mobile devices.
MobileVLM V2: Faster and Stronger Baseline for Vision Language Model
We introduce MobileVLM V2, a family of significantly improved vision language models upon MobileVLM, which proves that a delicate orchestration of novel architectural design, an improved training scheme tailored for mobile VLMs, and rich high-quality dataset curation can substantially benefit VLMs' performance.
End-to-End Video Instance Segmentation with Transformers
Here, we propose a new video instance segmentation framework built upon Transformers, termed VisTR, which views the VIS task as a direct end-to-end parallel sequence decoding/prediction problem.
Ranked #33 on
Video Instance Segmentation
on YouTube-VIS validation
Light-Weight RefineNet for Real-Time Semantic Segmentation
We consider an important task of effective and efficient semantic image segmentation.
Ranked #2 on
Real-Time Semantic Segmentation
on NYU Depth v2
Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video
To the best of our knowledge, this is the first work to show that deep networks trained using unlabelled monocular videos can predict globally scale-consistent camera trajectories over a long video sequence.
Ranked #61 on
Monocular Depth Estimation
on KITTI Eigen split
Unsupervised Scale-consistent Depth Learning from Video
We propose a monocular depth estimator SC-Depth, which requires only unlabelled videos for training and enables the scale-consistent prediction at inference time.
Structured Knowledge Distillation for Dense Prediction
Here we propose to distill structured knowledge from large networks to compact networks, taking into account the fact that dense prediction is a structured prediction problem.
Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image
State-of-the-art (SOTA) monocular metric depth estimation methods can only handle a single camera model and are unable to perform mixed-data training due to the metric ambiguity.
Ranked #19 on
Monocular Depth Estimation
on NYU-Depth V2
(using extra training data)
Metric3D v2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation
Our method benefits various applications including in-the-wild metrology monocular-SLAM, and 3D reconstruction, which highlight the versatility of Metric3D v2 models as geometric foundation models.
Ranked #1 on
Monocular Depth Estimation
on NYU-Depth V2
(using extra training data)
RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation
Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense classification problems such as semantic segmentation.
Ranked #13 on
Semantic Segmentation
on Trans10K
DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning
We employ the Earth Mover's Distance (EMD) as a metric to compute a structural distance between dense image representations to determine image relevance.
StyleAvatar3D: Leveraging Image-Text Diffusion Models for High-Fidelity 3D Avatar Generation
The recent advancements in image-text diffusion models have stimulated research interest in large-scale 3D generative models.
Visual Question Answering: A Survey of Methods and Datasets
Visual Question Answering (VQA) is a challenging task that has received increasing attention from both the computer vision and the natural language processing communities.
PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text
By systematically comparing with existing scene text representations, we show that our kernel representation can not only describe arbitrarily-shaped text but also well distinguish adjacent text.
Scene Text Image Super-Resolution in the Wild
For example, it outperforms LapSRN by over 5% and 8%on the recognition accuracy of ASTER and CRNN.
Auto-Rectify Network for Unsupervised Indoor Depth Estimation
However, excellent results have mostly been obtained in street-scene driving scenarios, and such methods often fail in other settings, particularly indoor videos taken by handheld devices.
Ranked #62 on
Monocular Depth Estimation
on NYU-Depth V2
SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenes
Self-supervised monocular depth estimation has shown impressive results in static scenes.
Indoor Monocular Depth Estimation
Monocular Depth Estimation
+1
Indices Matter: Learning to Index for Deep Image Matting
We show that existing upsampling operators can be unified with the notion of the index function.
Index Network
By viewing the indices as a function of the feature map, we introduce the concept of "learning to index", and present a novel index-guided encoder-decoder framework where indices are self-learned adaptively from data and are used to guide the downsampling and upsampling stages, without extra training supervision.
Ranked #2 on
Grayscale Image Denoising
on Set12 sigma30
TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation
Although vision transformers (ViTs) have achieved great success in computer vision, the heavy computational cost hampers their applications to dense prediction tasks such as semantic segmentation on mobile devices.
Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching
In this work, we present Matcher, a novel perception paradigm that utilizes off-the-shelf vision foundation models to address various perception tasks.
Wider or Deeper: Revisiting the ResNet Model for Visual Recognition
As a result, we are able to derive a new, shallower, architecture of residual networks which significantly outperforms much deeper models such as ResNet-200 on the ImageNet classification dataset.
Ranked #11 on
Semantic Segmentation
on PASCAL VOC 2012 test
Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells
While most results in this domain have been achieved on image classification and language modelling problems, here we concentrate on dense per-pixel tasks, in particular, semantic image segmentation using fully convolutional networks.
Ranked #13 on
Semantic Segmentation
on PASCAL VOC 2012 val
An end-to-end TextSpotter with Explicit Alignment and Attention
This allows the two tasks to work collaboratively by shar- ing convolutional features, which is critical to identify challenging text instances.
Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models
Our vid2vid-zero leverages off-the-shelf image diffusion models, and doesn't require training on any video.
FreeSOLO: Learning to Segment Objects without Annotations
FreeSOLO further demonstrates superiority as a strong pre-training method, outperforming state-of-the-art self-supervised pre-training methods by +9. 8% AP when fine-tuning instance segmentation with only 5% COCO masks.
PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm
In this paper, we introduce a novel universal 3D pre-training framework designed to facilitate the acquisition of efficient 3D representation, thereby establishing a pathway to 3D foundational models.
Ranked #1 on
3D Semantic Segmentation
on ScanNet++
(using extra training data)
Efficient Semantic Video Segmentation with Per-frame Inference
For semantic segmentation, most existing real-time deep models trained with each frame independently may produce inconsistent results for a video sequence.
Ranked #2 on
Video Semantic Segmentation
on CamVid
Deep Weakly-supervised Anomaly Detection
To detect both seen and unseen anomalies, we introduce a novel deep weakly-supervised approach, namely Pairwise Relation prediction Network (PReNet), that learns pairwise relation features and anomaly scores by predicting the relation of any two randomly sampled training instances, in which the pairwise relation can be anomaly-anomaly, anomaly-unlabeled, or unlabeled-unlabeled.
Deep Anomaly Detection with Deviation Networks
Instead of representation learning, our method fulfills an end-to-end learning of anomaly scores by a neural deviation learning, in which we leverage a few (e. g., multiple to dozens) labeled anomalies and a prior probability to enforce statistically significant deviations of the anomaly scores of anomalies from that of normal data objects in the upper tail.
Ranked #1 on
Network Intrusion Detection
on NB15-Backdoor
Unsupervised Representation Learning by Predicting Random Distances
To enable unsupervised learning on those domains, in this work we propose to learn features without using any labelled data by training neural networks to predict data distances in a randomly projected space.
CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation
Convolutional neural networks (CNNs) have been the de facto standard for nowadays 3D medical image segmentation.
VisionLLaMA: A Unified LLaMA Interface for Vision Tasks
Large language models are built on top of a transformer-based architecture to process textual inputs.
DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models
To showcase the power of the proposed approach, we generate datasets with rich dense pixel-wise labels for a wide range of downstream tasks, including semantic segmentation, instance segmentation, and depth estimation.
Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection
More importantly, based on OBD, we provide a detailed analysis of the impact of a collection of refinements, which may inspire others to build state-of-the-art text detectors.
Ranked #3 on
Scene Text Detection
on ICDAR 2017 MLT
FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors
We present a novel deep end-to-end trainable Face Super-Resolution Network (FSRNet), which makes full use of the geometry prior, i. e., facial landmark heatmaps and parsing maps, to super-resolve very low-resolution (LR) face images without well-aligned requirement.
Associatively Segmenting Instances and Semantics in Point Clouds
A 3D point cloud describes the real scene precisely and intuitively. To date how to segment diversified elements in such an informative 3D scene is rarely discussed.
Ranked #15 on
3D Instance Segmentation
on S3DIS
(mRec metric)
Context Prior for Scene Segmentation
Given an input image and corresponding ground truth, Affinity Loss constructs an ideal affinity map to supervise the learning of Context Prior.
Ranked #1 on
Scene Understanding
on ADE20K val
Repulsion Loss: Detecting Pedestrians in a Crowd
In this paper, we first explore how a state-of-the-art pedestrian detector is harmed by crowd occlusion via experimentation, providing insights into the crowd occlusion problem.
Ranked #9 on
Pedestrian Detection
on Caltech
(using extra training data)
FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation
Experiments on both synthetic Sintel data and real-world KITTI datasets demonstrate the effectiveness of the proposed approach, which needs only 1/10 computation of comparable networks to achieve on par accuracy.
Ranked #12 on
Optical Flow Estimation
on KITTI 2012
DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data
Compared with previous learning objectives, i. e., learning metric depth or relative depth, we propose to learn the affine-invariant depth using our diverse dataset to ensure both generalization and high-quality geometric shapes of scenes.
Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations
Deployment of deep learning models in robotics as sensory information extractors can be a daunting task to handle, even using generic GPU cards.
Ranked #6 on
Real-Time Semantic Segmentation
on NYU Depth v2
NAS-FCOS: Efficient Search for Object Detection Architectures
Neural Architecture Search (NAS) has shown great potential in effectively reducing manual effort in network design by automatically discovering optimal architectures.
CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning
Recent progress in semantic segmentation is driven by deep Convolutional Neural Networks and large-scale labeled image datasets.
Ranked #86 on
Few-Shot Semantic Segmentation
on PASCAL-5i (5-Shot)
Conditional Positional Encodings for Vision Transformers
Built on PEG, we present Conditional Position encoding Vision Transformer (CPVT).
SegViT: Semantic Segmentation with Plain Vision Transformers
We explore the capability of plain Vision Transformers (ViTs) for semantic segmentation and propose the SegVit.
Ranked #4 on
Semantic Segmentation
on COCO-Stuff test
SegViTv2: Exploring Efficient and Continual Semantic Segmentation with Plain Vision Transformers
This paper investigates the capability of plain Vision Transformers (ViTs) for semantic segmentation using the encoder-decoder framework and introduces \textbf{SegViTv2}.
Ranked #16 on
Semantic Segmentation
on ADE20K
Poseur: Direct Human Pose Regression with Transformers
We propose a direct, regression-based approach to 2D human pose estimation from single images.
Ranked #2 on
Keypoint Detection
on MS COCO
DoDNet: Learning to segment multi-organ and tumors from multiple partially labeled datasets
To address this, we propose a dynamic on-demand network (DoDNet) that learns to segment multiple organs and tumors on partially labeled datasets.
Learning from partially labeled data for multi-organ and tumor segmentation
To address this, we propose a Transformer based dynamic on-demand network (TransDoDNet) that learns to segment organs and tumors on multiple partially labeled datasets.
Template-Based Automatic Search of Compact Semantic Segmentation Architectures
Automatic search of neural architectures for various vision and natural language tasks is becoming a prominent tool as it allows to discover high-performing structures on any dataset of interest.
Ranked #13 on
Semantic Segmentation
on CamVid
Attention-guided Network for Ghost-free High Dynamic Range Imaging
Ghosting artifacts caused by moving objects or misalignments is a key challenge in high dynamic range (HDR) imaging for dynamic scenes.
From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer
A dense region can always be divided until sub-region counts are within the previously observed closed set.
Ranked #3 on
Crowd Counting
on TRANCOS
From Open Set to Closed Set: Supervised Spatial Divide-and-Conquer for Object Counting
Visual counting, a task that aims to estimate the number of objects from an image/video, is an open-set problem by nature, i. e., the number of population can vary in [0, inf) in theory.
SPTS: Single-Point Text Spotting
For the first time, we demonstrate that training scene text spotting models can be achieved with an extremely low-cost annotation of a single-point for each instance.
Ranked #3 on
Text Spotting
on SCUT-CTW1500
SPTS v2: Single-Point Scene Text Spotting
Within the context of our SPTS v2 framework, our experiments suggest a potential preference for single-point representation in scene text spotting when compared to other representations.
Ranked #15 on
Text Spotting
on ICDAR 2015
DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution
Previous top-performing approaches for point cloud instance segmentation involve a bottom-up strategy, which often includes inefficient operations or complex pipelines, such as grouping over-segmented components, introducing additional steps for refining, or designing complicated loss functions.
Dynamic Convolution for 3D Point Cloud Instance Segmentation
The proposed approach is proposal-free, and instead exploits a convolution process that adapts to the spatial and semantic characteristics of each instance.
SegPrompt: Boosting Open-world Segmentation via Category-level Prompt Learning
In this work, we propose a novel training mechanism termed SegPrompt that uses category information to improve the model's class-agnostic segmentation ability for both known and unknown categories.
REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments
One of the long-term challenges of robotics is to enable robots to interact with humans in the visual world via natural language, as humans are visual animals that communicate through language.
Self-training with progressive augmentation for unsupervised cross-domain person re-identification
In this work, we develop a self-training method with progressive augmentation framework (PAST) to promote the model performance progressively on the target dataset.
Ranked #11 on
Unsupervised Domain Adaptation
on Market to Duke
Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
We propose to symmetrically link convolutional and de-convolutional layers with skip-layer connections, with which the training converges much faster and attains a higher-quality local optimum.
Ranked #37 on
Image Super-Resolution
on BSD100 - 4x upscaling
End-to-End Video Text Spotting with Transformer
Recent video text spotting methods usually require the three-staged pipeline, i. e., detecting text in individual images, recognizing localized text, tracking text streams with post-processing to generate final results.
Segmenting Transparent Objects in the Wild
To address this important problem, this work proposes a large-scale dataset for transparent object segmentation, named Trans10K, consisting of 10, 428 images of real scenarios with carefully manual annotations, which are 10 times larger than the existing datasets.
Ranked #4 on
Semantic Segmentation
on Trans10K
DisCo: Remedy Self-supervised Learning on Lightweight Models with Distilled Contrastive Learning
Specifically, we find the final embedding obtained by the mainstream SSL methods contains the most fruitful information, and propose to distill the final embedding to maximally transmit a teacher's knowledge to a lightweight model by constraining the last embedding of the student to be consistent with that of the teacher.
TextSR: Content-Aware Text Super-Resolution Guided by Recognition
Nonetheless, most of the previous methods may not work well in recognizing text with low resolution which is often seen in natural scene images.
Deepfake Generation and Detection: A Benchmark and Survey
Deepfake is a technology dedicated to creating highly realistic facial images and videos under specific conditions, which has significant application potential in fields such as entertainment, movie production, digital human creation, to name a few.
Paragraph-to-Image Generation with Information-Enriched Diffusion Model
In this paper, we introduce an information-enriched diffusion model for paragraph-to-image generation task, termed ParaDiffusion, which delves into the transference of the extensive semantic comprehension capabilities of large language models to the task of image generation.
StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data
However, these datasets often exhibit domain bias, potentially constraining the generative capabilities of the models.
Ranked #53 on
Visual Question Answering
on MM-Vet
Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction
As it is hard to calibrate single-view RGB images in the wild, existing 3D human mesh reconstruction (3DHMR) methods either use a constant large focal length or estimate one based on the background environment context, which can not tackle the problem of the torso, limb, hand or face distortion caused by perspective camera projection when the camera is close to the human body.
Ranked #5 on
3D Human Pose Estimation
on 3DPW
Efficient Decoder-free Object Detection with Transformers
A natural usage of ViTs in detection is to replace the CNN-based backbone with a transformer-based backbone, which is straightforward and effective, with the price of bringing considerable computation burden for inference.
Explainable Deep Few-shot Anomaly Detection with Deviation Networks
Here, we study the problem of few-shot anomaly detection, in which we aim at using a few labeled anomaly examples to train sample-efficient discriminative detection models.
Ranked #5 on
Supervised Anomaly Detection
on MVTec AD
(using extra training data)
AE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text Spotting
Unlike previous works that merely employed visual features for text detection, this work proposes a novel text spotter, named Ambiguity Eliminating Text Spotter (AE TextSpotter), which learns both visual and linguistic features to significantly reduce ambiguity in text detection.
Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection
Despite most existing anomaly detection studies assume the availability of normal training samples only, a few labeled anomaly examples are often available in many real-world applications, such as defect samples identified during random quality inspection, lesion images confirmed by radiologists in daily medical screening, etc.
Ranked #4 on
Supervised Anomaly Detection
on MVTec AD
(using extra training data)
RGM: A Robust Generalizable Matching Model
Finding corresponding pixels within a pair of images is a fundamental computer vision task with various applications.
AQD: Towards Accurate Fully-Quantized Object Detection
Network quantization allows inference to be conducted using low-precision arithmetic for improved inference efficiency of deep neural networks on edge devices.
CTVIS: Consistent Training for Online Video Instance Segmentation
The discrimination of instance embeddings plays a vital role in associating instances across time for online video instance segmentation (VIS).
Ranked #2 on
Video Instance Segmentation
on Youtube-VIS 2022 Validation
(using extra training data)
Task-Aware Monocular Depth Estimation for 3D Object Detection
In this paper, we first analyse the data distributions and interaction of foreground and background, then propose the foreground-background separated monocular depth estimation (ForeSeE) method, to estimate the foreground depth and background depth using separate optimization objectives and depth decoders.
When Unsupervised Domain Adaptation Meets Tensor Representations
Domain adaption (DA) allows machine learning methods trained on data sampled from one distribution to be applied to data sampled from another.
Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrieval
In this framework, the anomaly detection problem is solved via a cascade patch retrieval procedure that retrieves the nearest neighbors for each test image patch in a coarse-to-fine fashion.
Ranked #1 on
Supervised Anomaly Detection
on BTAD
A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation
Previous works [3, 27] fail to employ strong augmentation in pseudo label learning efficiently, as the large distribution change caused by strong augmentation harms the batch normalisation statistics.
PointAttN: You Only Need Attention for Point Cloud Completion
To solve the problems, we leverage the cross-attention and self-attention mechanisms to design novel neural network for processing point cloud in a per-point manner to eliminate kNNs.
Multi-marginal Wasserstein GAN
Multiple marginal matching problem aims at learning mappings to match a source domain to multiple target domains and it has attracted great attention in many applications, such as multi-domain image translation.
ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting
Previous methods can be roughly categorized into two groups: character-based and segmentation-based, which often require character-level annotations and/or complex post-processing due to the unstructured output.
Ranked #7 on
Text Spotting
on Inverse-Text
Generative Prompt Model for Weakly Supervised Object Localization
During training, GenPromp converts image category labels to learnable prompt embeddings which are fed to a generative model to conditionally recover the input image with noise and learn representative embeddings.
Ranked #1 on
Weakly-Supervised Object Localization
on CUB-200-2011
(Top-1 Localization Accuracy metric, using extra
training data)
A Mutual Bootstrapping Model for Automated Skin Lesion Segmentation and Classification
Our results suggest that it is possible to boost the performance of skin lesion segmentation and classification simultaneously via training a unified model to perform both tasks in a mutual bootstrapping way.
Towards Effective Low-bitwidth Convolutional Neural Networks
This paper tackles the problem of training a deep convolutional neural network with both low-precision weights and low-bitwidth activations.
Super Vision Transformer
Experimental results on ImageNet demonstrate that our SuperViT can considerably reduce the computational costs of ViT models with even performance increase.
Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation
In contrast, human vision is able to predict poses by exploiting geometric constraints of joint inter-connectivity.
Ranked #15 on
Pose Estimation
on MPII Human Pose
Mining Mid-level Visual Patterns with Deep CNN Activations
The purpose of mid-level visual element discovery is to find clusters of image patches that are both representative and discriminative.
Learning Affinity-Aware Upsampling for Deep Image Matting
By looking at existing upsampling operators from a unified mathematical perspective, we generalize them into a second-order form and introduce Affinity-Aware Upsampling (A2U) where upsampling kernels are generated using a light-weight lowrank bilinear model and are conditioned on second-order features.
Reading Car License Plates Using Deep Convolutional Neural Networks and LSTMs
Inspired by the success of deep neural networks (DNNs) in various vision applications, here we leverage DNNs to learn high-level features in a cascade framework, which lead to improved performance on both detection and recognition.
Learning Deep Gradient Descent Optimization for Image Deconvolution
Extensive experiments on synthetic benchmarks and challenging real-world images demonstrate that the proposed deep optimization method is effective and robust to produce favorable results as well as practical for real-world image deblurring applications.
Exploiting temporal consistency for real-time video depth estimation
The temporal consistency loss is combined with the spatial loss to update the model in an end-to-end fashion.
Ranked #5 on
Monocular Depth Estimation
on Mid-Air Dataset
Part-Guided Attention Learning for Vehicle Instance Retrieval
Finally, we aggregate the global appearance and part features to improve the feature performance further.
Weighing Counts: Sequential Crowd Counting by Reinforcement Learning
Inspired by scale weighing, we propose a novel 'counting scale' termed LibraNet where the count value is analogized by weight.
Training Protocol Matters: Towards Accurate Scene Text Recognition via Training Protocol Searching
The development of scene text recognition (STR) in the era of deep learning has been mainly focused on novel architectures of STR models.
Viral Pneumonia Screening on Chest X-ray Images Using Confidence-Aware Anomaly Detection
In this paper, we formulate the task of differentiating viral pneumonia from non-viral pneumonia and healthy controls into an one-class classification-based anomaly detection problem, and thus propose the confidence-aware anomaly detection (CAAD) model, which consists of a shared feature extractor, an anomaly detection module, and a confidence prediction module.
Toward Deep Supervised Anomaly Detection: Reinforcement Learning from Partially Labeled Anomaly Data
We consider the problem of anomaly detection with a small set of partially labeled anomaly examples and a large-scale unlabeled dataset.
DENSE: Data-Free One-Shot Federated Learning
One-shot Federated Learning (FL) has recently emerged as a promising approach, which allows the central server to learn a model in a single communication round.
Fully Quantized Image Super-Resolution Networks
With the rising popularity of intelligent mobile devices, it is of great practical significance to develop accurate, realtime and energy-efficient image Super-Resolution (SR) inference methods.
Dynamic Neural Representational Decoders for High-Resolution Semantic Segmentation
This neural representation enables our decoder to leverage the smoothness prior in the semantic label space, and thus makes our decoder more efficient.
Multi-dataset Training of Transformers for Robust Action Recognition
We study the task of robust feature representations, aiming to generalize well on multiple datasets for action recognition.
Hyperspectral Classification Based on Lightweight 3-D-CNN With Transfer Learning
In contrast to previous approaches, we do not impose restrictions over the source data sets, in which they do not have to be collected by the same sensors as the target data sets.
Bootstrapping the Performance of Webly Supervised Semantic Segmentation
In this work, we focus on weak supervision, developing a method for training a high-quality pixel-level classifier for semantic segmentation, using only image-level class labels as the provided ground-truth.
Memory-Efficient Hierarchical Neural Architecture Search for Image Denoising
We also present analysis on the architectures found by NAS.
Memory-Efficient Hierarchical Neural Architecture Search for Image Restoration
For the inner search space, we propose a layer-wise architecture sharing strategy (LWAS), resulting in more flexible architectures and better performance.
Learning Conditional Attributes for Compositional Zero-Shot Learning
Compositional Zero-Shot Learning (CZSL) aims to train models to recognize novel compositional concepts based on learned concepts such as attribute-object combinations.
Ranked #1 on
Compositional Zero-Shot Learning
on MIT-States
Robust Data Hiding Using Inverse Gradient Attention
In deep data hiding models, to maximize the encoding capacity, each pixel of the cover image ought to be treated differently since they have different sensitivities w. r. t.
Learning Deep Representations Using Convolutional Auto-encoders with Symmetric Skip Connections
In this paper, we investigate convolutional denoising auto-encoders to show that unsupervised pre-training can still improve the performance of high-level image related tasks such as image classification and semantic segmentation.
Deep CNNs With Spatially Weighted Pooling for Fine-Grained Car Recognition
By applying our method to several fine-grained car recognition data sets, we demonstrate that the proposed method can achieve better performance than recent approaches in the literature.
Ranked #1 on
Fine-Grained Image Classification
on CarFlag-563
Traffic Scene Parsing through the TSP6K Dataset
To date, most existing datasets focus on autonomous driving scenes.
Learning to predict crisp boundaries
Recent methods for boundary or edge detection built on Deep Convolutional Neural Networks (CNNs) typically suffer from the issue of predicted edges being thick and need post-processing to obtain crisp boundaries.
TSGB: Target-Selective Gradient Backprop for Probing CNN Visual Saliency
Inspired by those observations, we propose a novel visual saliency method, termed Target-Selective Gradient Backprop (TSGB), which leverages rectification operations to effectively emphasize target classes and further efficiently propagate the saliency to the image space, thereby generating target-selective and fine-grained saliency maps.
FoPro: Few-Shot Guided Robust Webly-Supervised Prototypical Learning
Most existing methods focus on learning noise-robust models from web images while neglecting the performance drop caused by the differences between web domain and real-world domain.
DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models
In contrast, synthetic data can be freely available using a generative model (e. g., DALL-E, Stable Diffusion).
DA-STC: Domain Adaptive Video Semantic Segmentation via Spatio-Temporal Consistency
To solve the challenge, we propose a novel DA-STC method for domain adaptive video semantic segmentation, which incorporates a bidirectional multi-level spatio-temporal fusion module and a category-aware spatio-temporal feature alignment module to facilitate consistent learning for domain-invariant features.
Regularizing Proxies with Multi-Adversarial Training for Unsupervised Domain-Adaptive Semantic Segmentation
To tackle the unsupervised domain adaptation problem, we explore the possibilities to generate high-quality labels as proxy labels to supervise the training on target data.
Piecewise classifier mappings: Learning fine-grained learners for novel categories with few examples
To solve this problem, we propose an end-to-end trainable deep network which is inspired by the state-of-the-art fine-grained recognition model and is tailored for the FSFG task.
Real-time End-to-End Video Text Spotter with Contrastive Representation Learning
Our contributions are three-fold: 1) CoText simultaneously address the three tasks (e. g., text detection, tracking, recognition) in a real-time end-to-end trainable framework.
Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
Therefore, here we present a deep convolutional neural field model for estimating depths from single monocular images, aiming to jointly explore the capacity of deep CNN and continuous CRF.
The Treasure beneath Convolutional Layers: Cross-convolutional-layer Pooling for Image Classification
This paper, however, advocates that if used appropriately convolutional layer activations can be turned into a powerful image representation which enjoys many advantages over fully-connected layer activations.
Improving Generative Adversarial Networks with Local Coordinate Coding
In this paper, rather than sampling from the predefined prior distribution, we propose an LCCGAN model with local coordinate coding (LCC) to improve the performance of generating data.
What value do explicit high level concepts have in vision to language problems?
Much of the recent progress in Vision-to-Language (V2L) problems has been achieved through a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs).
Adversarial Learning with Local Coordinate Coding
Generative adversarial networks (GANs) aim to generate realistic data from some prior distribution (e. g., Gaussian noises).
Adaptive Importance Learning for Improving Lightweight Image Super-resolution Network
In this study, we revisit this problem from an orthog- onal view, and propose a novel learning strategy to maxi- mize the pixel-wise fitting capacity of a given lightweight network architecture.
Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization
In contrast, human vision is able to predict poses by exploiting geometric constraints of landmark point inter-connectivity.
Monocular Depth Estimation with Augmented Ordinal Depth Relationships
In this paper, we propose to improve the performance of metric depth estimation with relative depths collected from stereo movie videos using existing stereo matching algorithm.
Multi-label Learning Based Deep Transfer Neural Network for Facial Attribute Classification
To address the above problem, we propose a novel deep transfer neural network method based on multi-label learning for facial attribute classification, termed FMTNet, which consists of three sub-networks: the Face detection Network (FNet), the Multi-label learning Network (MNet) and the Transfer learning Network (TNet).
Salient Object Detection by Lossless Feature Reflection
Inspired by the intrinsic reflection of natural images, in this paper we propose a novel feature learning framework for large-scale salient object detection.
HyperFusion-Net: Densely Reflective Fusion for Salient Object Detection
Salient object detection (SOD), which aims to find the most important region of interest and segment the relevant object/item in that area, is an important yet challenging vision task.
VITAL: VIsual Tracking via Adversarial Learning
To augment positive samples, we use a generative network to randomly generate masks, which are applied to adaptively dropout input features to capture a variety of appearance changes.
Visual Question Answering with Memory-Augmented Networks
In this paper, we exploit a memory-augmented neural network to predict accurate answers to visual questions, even when those answers occur rarely in the training set.
Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation
In our work, we focus on the weakly supervised semantic segmentation with image label annotations.
Non-rigid Object Tracking via Deep Multi-scale Spatial-temporal Discriminative Saliency Maps
Extensive experiments demonstrate that the proposed algorithm achieves competitive performance in both saliency detection and visual tracking, especially outperforming other related trackers on the non-rigid object tracking datasets.
Agile Amulet: Real-Time Salient Object Detection with Contextual Attention
This paper proposes an Agile Aggregating Multi-Level feaTure framework (Agile Amulet) for salient object detection.
Automatic Image Cropping for Visual Aesthetic Enhancement Using Deep Neural Networks and Cascaded Regression
The deep CNN model is then designed to extract features from several image cropping datasets, upon which the cropping bounding boxes are predicted by the proposed CCR method.
Real-time Semantic Image Segmentation via Spatial Sparsity
We propose an approach to semantic (image) segmentation that reduces the computational costs by a factor of 25 with limited impact on the quality of results.
Asking the Difficult Questions: Goal-Oriented Visual Question Generation via Intermediate Rewards
Despite significant progress in a variety of vision-and-language problems, developing a method capable of asking intelligent, goal-oriented questions about images is proven to be an inscrutable challenge.
Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning
The Visual Dialogue task requires an agent to engage in a conversation about an image with a human.
Ranked #4 on
Visual Dialog
on VisDial v0.9 val
Kill Two Birds with One Stone: Weakly-Supervised Neural Network for Image Annotation and Tag Refinement
These comments can be a description of the image, or some objects, attributes, scenes in it, which are normally used as the user-provided tags.
Parallel Attention: A Unified Framework for Visual Object Discovery through Dialogs and Queries
To this end we propose a unified framework, the ParalleL AttentioN (PLAN) network, to discover the object in an image that is being referred to in variable length natural expression descriptions, from short phrases query to long multi-round dialogs.
Adversarial Generation of Training Examples: Applications to Moving Vehicle License Plate Recognition
Our experimental results on a few data sets demonstrate the effectiveness of using GAN images: an improvement of 7. 5% over a strong baseline with moderate-sized real data being available.
Towards End-to-End Car License Plates Detection and Recognition with Deep Neural Networks
In contrast to existing approaches which take license plate detection and recognition as two separate tasks and settle them step by step, our method jointly solves these two tasks by a single network.
Estimating Depth from Monocular Images as Classification Using Deep Fully Convolutional Residual Networks
Then we train fully convolutional deep residual networks to predict the depth label of each pixel.
FVQA: Fact-based Visual Question Answering
We evaluate several baseline models on the FVQA dataset, and describe a novel model which is capable of reasoning about an image on the basis of supporting facts.
Ranked #2 on
Visual Question Answering (VQA)
on F-VQA
Weakly Supervised Semantic Segmentation Based on Web Image Co-segmentation
Training a Fully Convolutional Network (FCN) for semantic segmentation requires a large number of masks with pixel level labelling, which involves a large amount of human labour and time for annotation.
Beyond Low Rank: A Data-Adaptive Tensor Completion Method
The prior for the non-low-rank structure is established based on a mixture of Gaussians which is shown to be flexible enough, and powerful enough, to inform the completion process for a variety of real tensor data.
Relative Depth Order Estimation Using Multi-scale Densely Connected Convolutional Networks
We study the problem of estimating the relative depth order of point pairs in a monocular image.
Unsupervised Object Discovery and Co-Localization by Deep Descriptor Transforming
Reusable model design becomes desirable with the rapid expansion of computer vision and machine learning applications.
Ranked #11 on
Single-object discovery
on COCO_20k
Visually Aligned Word Embeddings for Improving Zero-shot Learning
To overcome this visual-semantic discrepancy, this work proposes an objective function to re-align the distributed word embeddings with visual information by learning a neural network to map it into a new representation called visually aligned word embedding (VAWE).
Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks
In this work, we jointly address the problem of text detection and recognition in natural scene images based on convolutional recurrent neural networks.
TasselNet: Counting maize tassels in the wild via local counts regression network
To our knowledge, this is the first time that a plant-related counting problem is considered using computer vision technologies under unconstrained field-based environment.
Care about you: towards large-scale human-centric visual relationship detection
In addressing this problem we first construct a large-scale human-centric visual relationship detection dataset (HCVRD), which provides many more types of relationship annotation (nearly 10K categories) than the previous released datasets.
Human-Object Interaction Detection
Relationship Detection
+1
Deep Descriptor Transforming for Image Co-Localization
Reusable model design becomes desirable with the rapid expansion of machine learning applications.
Exploring Context with Deep Structured models for Semantic Segmentation
We formulate deep structured models by combining CNNs and Conditional Random Fields (CRFs) for learning the patch-patch context between image regions.
Towards Context-aware Interaction Recognition
Recognizing how objects interact with each other is a crucial task in visual recognition.
Robust Guided Image Filtering
In this paper, we propose a general framework for Robust Guided Image Filtering (RGIF), which contains a data term and a smoothness term, to solve the two issues mentioned above.
Structured Learning of Tree Potentials in CRF for Image Segmentation
In this fashion, we easily achieve nonlinear learning of potential functions on both unary and pairwise terms in CRFs.
Multi-Label Image Classification with Regional Latent Semantic Dependencies
Recent state-of-the-art approaches to multi-label image classification exploit the label dependencies in an image, at global level, largely improving the labeling capacity.
Learning Multi-level Region Consistency with Dense Multi-label Networks for Semantic Segmentation
Semantic image segmentation is a fundamental task in image understanding.
Deep Learning Features at Scale for Visual Place Recognition
The success of deep learning techniques in the computer vision domain has triggered a range of initial investigations into their utility for visual place recognition, all using generic features from networks that were trained for other types of recognition tasks.
Compositional Model based Fisher Vector Coding for Image Classification
To handle this limitation, in this paper we break the convention which assumes that a local feature is drawn from one of few Gaussian distributions.
Cross-convolutional-layer Pooling for Image Recognition
Most of these studies adopt activations from a single DCNN layer, usually the fully-connected layer, as the image representation.
Image Captioning and Visual Question Answering Based on Attributes and External Knowledge
Much recent progress in Vision-to-Language problems has been achieved through a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs).
The VQA-Machine: Learning How to Use Existing Vision Algorithms to Answer New Questions
To train a method to perform even one of these operations accurately from {image, question, answer} tuples would be challenging, but to aim to achieve them all with a limited set of such training data seems ambitious at best.
From Motion Blur to Motion Flow: a Deep Learning Solution for Removing Heterogeneous Motion Blur
The critical observation underpinning our approach is thus that learning the motion flow instead allows the model to focus on the cause of the blur, irrespective of the image content.
Sequential Person Recognition in Photo Albums with a Recurrent Network
In this work, we propose to model the relational information between people as a sequence prediction task.
Attend in groups: a weakly-supervised deep learning framework for learning from web data
Large-scale datasets have driven the rapid development of deep neural networks for visual recognition.
Exploiting Depth from Single Monocular Images for Object Detection and Semantic Segmentation
Augmenting RGB data with measured depth has been shown to improve the performance of a range of tasks in computer vision including object detection and semantic segmentation.
Fast Training of Triplet-based Deep Binary Embedding Networks
To solve the first stage, we design a large-scale high-order binary codes inference algorithm to reduce the high-order objective to a standard binary quadratic problem such that graph cuts can be used to efficiently infer the binary code which serve as the label of each training datum.
Image Co-localization by Mimicking a Good Detector's Confidence Score Distribution
More specifically, we observe that given a set of object proposals extracted from an image that contains the object of interest, an accurate strongly supervised object detector should give high scores to only a small minority of proposals, and low scores to most of them.
Where to Focus: Query Adaptive Matching for Instance Retrieval Using Convolutional Feature Maps
Instance retrieval requires one to search for images that contain a particular object within a large corpus.
